Knowledge catalogue
arXiv:2602.21203v2 Announce Type: replace-cross Abstract: Visual reinforcement learning is appealing for robotics but expensive. Off-policy methods are sample-efficient yet slow while on-policy method
This dismissal of AI skepticism is egregiously wrong, or at least deeply selective, @jeffclune. Was I wrong that pure LLMs would always be vulnerable to hallucinations? Was I wrong that pure LLMs woul
This is actually an example of why Astra is not artificial general intelligence (AGI). I see the same issues with visual perception demos ie using brightly colored simple shaped objects on a simple ba
arXiv:2609.04305v1 Announce Type: cross Abstract: We present TNFlow, a transformer and normalizing flow architecture for inferring the surface composition of Trans-Neptunian Objects (TNOs) from their
arXiv:2609.05369v1 Announce Type: cross Abstract: Vision-language-action (VLA) models can execute short manipulation skills, but remain brittle in long-horizon procedures requiring persistent task sta
arXiv:2609.04678v1 Announce Type: new Abstract: Existing post-training pipelines for coding and terminal agents suffer severe token and control fidelity errors: simplified training environments mismat
arXiv:2609.04242v1 Announce Type: cross Abstract: Audio-visual understanding remains challenging because models must jointly interpret spoken content, visual events, and their temporal relationships.
arXiv:2609.05415v1 Announce Type: new Abstract: Recent advances in automatic rigging now deliver animation-ready 3D assets at scale, yet generating the motion to drive them remains a bottleneck. Exist
arXiv:2609.04948v1 Announce Type: cross Abstract: Multi-expert models have become the dominant paradigm for long-tailed learning, largely attributed to their presumed ability to benefit from expert di
arXiv:2609.04355v1 Announce Type: cross Abstract: Pretrained vision-language-action (VLA) models enable broad manipulation but remain unreliable in tasks demanding precision and repeatability. Applyin
arXiv:2609.05198v1 Announce Type: new Abstract: On-Policy Distillation (OPD) has emerged as a widely adopted post-training paradigm for enhancing large language models in reasoning domains. However, t
arXiv:2609.05376v1 Announce Type: cross Abstract: Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet fail when visually similar objects or receptacl
Banger paper from Google DeepMind. Every AI weather model so far has been trained and initialized on analysis data, which is itself the output of another model. That means the forecast inherits whatev
hmm. can anybody point to a quote where OpenAI publicly advocated neurosymbolic AI? i have seen explicitly positive words about neurosymbolic AI from Google, Amazon, IBM, Anthropic, etc. but am not aw
I read some strange criticisms of this post. So here is my take. I’m not fully endorsing the piece by Newport, but there’s quite some factually true information in it. Responsible and careful people (
OpenAI’s chief scientist: “The idea of racing forward at all costs seems absurd once one internalizes the seriousness of the stakes.” I wrote about the state of AI, why I’m concerned about the next fe
OpenAI’s CISO🤦♂️ Well let’s dive into this—shall we Below is a screenshot of Open AI’s Chief Information Security Officer Dane Stuckey who during work hours is on X shit posting under his alt but for
🚨scoop from @theinformation: Anthropic (which has yet to established stable profitability) has committed to $517 billion in compute deals - almost 3x what they had previously told investors. by my est
Listen to my conversation with @GaryMarcus about why he’s stated that OpenAI needs to Pause NOW. Gary’s not ready to pause all frontier AI, but Pause is a solution to many problems, including OpenAI’s
me: AI isn’t that smart & remains unreliable and now I am worried that monitoring-which likely could have prevented multiple incidents-is being reduced, and also worried that OpenAI has consistently n
This is a weird behavior in coding models and something worth looking into. It turns that some models over-edit code that another models wrote. There is a high chance that your repo now has commits fr
100%, which is the core of why I called for a pause on OpenAI in my newsletter today. The Hugging Face incident was probably just the tip of the iceberg. OpenAI has lost control and they're hiding imp
arXiv:2609.03794v1 Announce Type: new Abstract: Mobile robotic platforms offer a flexible alternative to fixed manipulators for non-destructive evaluation (NDE) of large aerospace structures, but thei
arXiv:2609.04177v1 Announce Type: new Abstract: Explaining why a specific outcome occurred, and which inputs deserve the blame or credit, is central to philosophical, scientific, and policy analysis.
arXiv:2609.04147v1 Announce Type: cross Abstract: This paper presents a low-cost, open experimental platform for research in end-to-end autonomous driving with miniature Ackermann vehicles. The platfo
arXiv:2511.02192v3 Announce Type: replace Abstract: This paper presents a quantitative comparison between centralised and distributed multi-agent reinforcement learning (MARL) architectures for contro
arXiv:2609.03366v1 Announce Type: new Abstract: Accountability means a decision can be examined, justified, and contested. LLMs make this hard: fluent output may be ungrounded, incomplete, or unfaithf
arXiv:2505.12037v2 Announce Type: replace Abstract: Learning the optimal policy for Markov decision process problems (MDPs) from samples is a fundamental problem in online and data-driven decision-mak
arXiv:2609.04096v1 Announce Type: cross Abstract: This paper proposes AdaRoboVLG, a task-adaptive Vision-Language-Grasp (VLG) framework that supports generalizable grasp synthesis across different rob
arXiv:2609.03258v1 Announce Type: new Abstract: Parking spot classification is a fundamental task in intelligent transportation systems, yet most deep learning approaches rely on large amounts of anno
'• And as a scientist, it’s disappointing that we don’t (yet) know much about how the system actually works.' This is so true. Hot take on OpenAI GPT-6 Astra*, with a challenge to @gdb’s claims about
arXiv:2609.03716v1 Announce Type: new Abstract: Data centers are increasingly optimized by artificial intelligence and, at the same time, increasingly loaded by it. The literature treats these as two
Astra is a genuine improvement but not even off trend. So much for GPT-6 being AGI, folks. (i think we can safely assume that real AGI would be significantly above the trend line,) GPT-6 Astra has set
arXiv:2609.03615v1 Announce Type: new Abstract: While deep generative models offer new opportunities for medical image synthesis and data sharing, their ability to memorize and reproduce training samp
arXiv:2609.03407v1 Announce Type: new Abstract: People increasingly turn to large language models (LLMs) for everyday advice, making ethically charged interpersonal problems a practical moral-advisory
arXiv:2609.03389v1 Announce Type: cross Abstract: Smectic liquid crystals are layered liquid-crystalline phases characterized by orientational order and periodic density modulation. Although their str
Crazy to see this. I have spent years saying that GenAI was unreliable and we can’t trust it. The fact that it cannot be trusted to follow instructions is a core part of the issue, as I have been poin
arXiv:2609.03894v1 Announce Type: new Abstract: Large language models (LLMs) have become ubiquitous tools for code generation and editing. However, development teams often use multiple LLM assistants.
arXiv:2609.03324v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves large language model reasoning, but its practical scaling is constrained by expensive on-
arXiv:2609.03432v1 Announce Type: new Abstract: Automated evaluation of creativity tasks remains challenging for LLM-as-a-Judge, as LLM is susceptible to biases such as verbosity bias and leniency bia
arXiv:2609.04011v1 Announce Type: cross Abstract: Reliable transport models are essential when modelling and optimising many chemical engineering processes, yet, most models assume hand-picked constit
arXiv:2609.03878v1 Announce Type: cross Abstract: Reconstruction-based anomaly detectors are accurate but opaque: a deep autoencoder flags a sample without telling a practitioner which feature ranges
Does Astra have human-like continual learning capability over long periods? If not, it's not AGI. Even a system that could pass @demishassabis's new 'Turing test' where it has to independently discove
arXiv:2609.04094v1 Announce Type: new Abstract: Reinforcement Learning from Verifiable Rewards works well when a task has a programmatic checker, but most long-horizon agent domains have none. We work
arXiv:2609.03846v1 Announce Type: cross Abstract: We study the allocation of indivisible goods among agents with identical additive valuations, focusing on envy-freeness up to one good (EF1) and Nash
arXiv:2609.03391v1 Announce Type: cross Abstract: Contrastive language-image learning (CLIP) has become a key paradigm for remote sensing vision-language understanding. However, existing remote sensin
arXiv:2609.03563v1 Announce Type: new Abstract: We present FlashRender, a few-step generative rendering framework that retakes a source video along a target camera trajectory in seconds. We identify s
arXiv:2609.03241v1 Announce Type: cross Abstract: A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse superv
arXiv:2609.03590v1 Announce Type: cross Abstract: Timely delivery of delay-sensitive information over dynamic, heterogeneous networks is essential for NextG interactive applications, yet providing str
arXiv:2609.03889v1 Announce Type: cross Abstract: Contact-rich loco-manipulation requires a bridge between semantic action generation and physical interaction control. Existing Vision-language-action
arXiv:2609.03868v1 Announce Type: cross Abstract: Target-centered gaze interaction requires more than suppressing frame-to-frame fluctuations: target acquisition produces task-aligned changes in gaze-
arXiv:2609.04193v1 Announce Type: new Abstract: Vision-language pre-training and predictive world modeling provide robot policies with rich semantic and dynamic visual features, but their native actio
Good old days at OpenAI in 2016: an agent stares at screen pixels, moves a mouse, and books a flight on United. We called it World of Bits, inside OpenAI Universe. 10 yrs later, Astra is reincarnated
arXiv:2609.03342v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) drives chain-of-thought reasoning in large language models, yet its binary outcome reward cannot d
arXiv:2609.02923v1 Announce Type: cross Abstract: We present a projected sensitivity study for hadronic mono-Z dark-matter production using CMS Run~2015D HTMHT open data corresponding to 2.256382381~i
arXiv:2609.03941v1 Announce Type: cross Abstract: RL-based post-training for reasoning models is increasingly bottlenecked by repeated fresh rollout generation, particularly in agentic settings where
arXiv:2511.07761v2 Announce Type: replace Abstract: High-altitude balloons (HABs) are common in scientific research due to their wide range of applications and low cost. Because of their nonlinear, un
arXiv:2609.03858v1 Announce Type: new Abstract: Attention mechanisms are central to modern foundation models, yet their training dynamics remain poorly understood, especially when the attention matric
Disaster recovery at scale is hard. Learn how Intuit built EWOK Agent, an agentic disaster recovery assistant on Amazon Bedrock that lets on-call engineers run production failovers from a plain-langua
arXiv:2609.03985v1 Announce Type: cross Abstract: Zero-shot vision-language models (VLMs) are increasingly used as training-free species recognizers, but reported accuracy can reflect more than visual